| import streamlit as st |
| from langchain.document_loaders import TextLoader |
| from langchain.document_loaders import UnstructuredFileLoader |
| from langchain.text_splitter import RecursiveCharacterTextSplitter |
| from langchain.embeddings import HuggingFaceEmbeddings |
| from langchain.vectorstores import FAISS |
| from langchain.chains import RetrievalQA |
| from langchain.llms import HuggingFaceHub |
| import tempfile |
| import os |
|
|
| @st.cache_resource |
| def load_vector_store(file_path): |
| |
| loader = TextLoader(file_path) |
| documents = loader.load() |
|
|
| splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50) |
| chunks = splitter.split_documents(documents) |
|
|
| |
| embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") |
| db = FAISS.from_documents(chunks, embedding_model) |
| return db |
|
|
| def main(): |
| st.title("📄 Ask Questions About Your Document") |
| st.write("Upload a `.txt` file and ask anything!") |
|
|
| uploaded_file = st.file_uploader("Upload a text file", type=["txt"]) |
|
|
| if uploaded_file: |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".txt") as tmp_file: |
| tmp_file.write(uploaded_file.read()) |
| tmp_path = tmp_file.name |
|
|
| db = load_vector_store(tmp_path) |
|
|
| query = st.text_input("Enter your question:") |
| if query: |
| qa_chain = RetrievalQA.from_chain_type( |
| llm=HuggingFaceHub( |
| repo_id="google/flan-t5-base", |
| model_kwargs={"temperature": 0.5, "max_length": 256} |
| ), |
| retriever=db.as_retriever(), |
| return_source_documents=True |
| ) |
|
|
| result = qa_chain.run(query) |
|
|
| st.write("### 📌 Answer") |
| st.write(result) |
|
|
| |
| os.remove(tmp_path) |
|
|
| if __name__ == "__main__": |
| main() |
|
|
